Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fast-Lio2 Performs Better #102

Open
celikemir opened this issue Oct 11, 2024 · 2 comments
Open

Fast-Lio2 Performs Better #102

celikemir opened this issue Oct 11, 2024 · 2 comments

Comments

@celikemir
Copy link

Hi,

I have several bag files recorded at different altitudes with a UAV, such as 50m, 100m, etc. The LiDAR is positioned at nadir, pointing downward. There is significant odometry degradation, particularly in some areas. I also tested the same bag files with FAST-LIO2, and its performance was better and closer to the ground truth. My question is: do you have any suggestions for adjusting parameters for outdoor use and fixing these degradation points? (I've already adjusted filter_size_surf, etc.) The odometry completely diverges in the opposite direction and fails to recover.

@sharknow
Copy link

Hi,

I have several bag files recorded at different altitudes with a UAV, such as 50m, 100m, etc. The LiDAR is positioned at nadir, pointing downward. There is significant odometry degradation, particularly in some areas. I also tested the same bag files with FAST-LIO2, and its performance was better and closer to the ground truth. My question is: do you have any suggestions for adjusting parameters for outdoor use and fixing these degradation points? (I've already adjusted filter_size_surf, etc.) The odometry completely diverges in the opposite direction and fails to recover.

Can you provide a picture with the results? Thank you!

@celikemir
Copy link
Author

celikemir commented Oct 11, 2024

Here are the results below, where you can easily distinguish which one diverges from the ground truth.
Ground truth, Point Lio, Fast-LIO respectively
50m
50m_pointlio
50m_newparam

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants